-
Using the latest Ogbujipt from Git, pgvector version 0.3.6 installed, and while initializing a DocDB instance via __DocDB.from_conn_params__ with the following:
```python
db = await DocDB.from…
-
## Is your feature request related to a problem? Please describe.
I'm also using Oracle Database 23ai and would like to assert the new data types provided in this version. For that the [documented …
-
In the place where i work [Cambá](www.camba.coop), we started to use page-assits to test our local ai server with ollama.
Going deeper on the extension features we found KNOWLEDGE BASE.
After tha…
josx updated
4 months ago
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
I have spent a few hours looking through the documentation and asking in the Discord. I'…
-
To help clean up the code, somthing that we do a lot is index collections of stuff, whether that is a local file system, a mongodb collection of discord messages, or a table of webpages scraped from s…
-
Compile a list of viable options along with relevant pros, cons, and questions to inform an appropriate choice.
-
### System Overview
A resume processing system is one that takes resumes uploaded by users, then extracts information about the resume and stores it in highly optimized databases for advanced search,…
-
-
**Task**: Create an endpoint for user to upload their documents onto our object storage (MinIO). Document will be indexed to our vector database through a pipeline.
**Output**: There is an endpoint…
-
Was there a reason to select Vespa as vector database.
Our company is using a different vector database and I am thinking, if I can vectorize/ index the data and use a different vector db to store…